Advertisement

Measuring Conceptual Incongruity from Text-Based Annotations

  • Nisheeth Srivastava
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11278)

Abstract

We propose a method for measuring the conceptual incongruity of a digital object using associated text meta-data. We show that this measure correlates well with empirical creativity ratings elicited from human subjects in laboratory settings. Extending our focus to online resources, we show that the predicted incongruity of a movie plot in the Movielens database is weakly correlated with users’ ratings for the movie, but strongly correlated with variability in ratings. Movies with incongruous plots appear to elicit much more polarized responses. Further, in domains where cognitive theories suggest users are likely to be looking for incongruity, e.g. humor, we show, using the Youtube Comedy Slam Dataset, that user ratings for comedy pieces are considerably well-predicted by their incongruity score. These evaluations provide convergent evidence for the validity of our incongruity measurement, and immediately present several direct application possibilities. We present a case example of including incongruity as a recommender system metric to diversify the set of suggestions made in response to user queries in ways that align with users’ natural curiosity.

Keywords

User modeling Cognitive psychology UI design 

References

  1. 1.
    Adamopoulos, P., Tuzhilin, A.: On unexpectedness in recommender systems: or how to better expect the unexpected. ACM Trans. Intell. Syst. Technol. (TIST) 5(4), 54 (2014)Google Scholar
  2. 2.
    Bollegala, D., Matsuo, Y., Ishizuka, M.: Measuring semantic similarity between words using web search engines. WWW 7, 757–766 (2007)Google Scholar
  3. 3.
    Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. (CSUR) 41(3), 15 (2009)CrossRefGoogle Scholar
  4. 4.
    Cilibrasi, R.L., Vitanyi, P.M.: The google similarity distance. IEEE Trans. Knowl. Data Eng. 19(3), 370–383 (2007)CrossRefGoogle Scholar
  5. 5.
    Clark, A.: Whatever next? predictive brains, situated agents, and the future of cognitive science. Behav. Brain Sci. 36(3), 181–204 (2013)CrossRefGoogle Scholar
  6. 6.
    Herlocker, J.L., Konstan, J.A., Terveen, L.G., Riedl, J.T.: Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst. (TOIS) 22(1), 5–53 (2004)CrossRefGoogle Scholar
  7. 7.
    Lops, P., de Gemmis, M., Semeraro, G.: Content-based recommender systems: state of the art and trends. In: Ricci, F., Rokach, L., Shapira, B., Kantor, P.B. (eds.) Recommender Systems Handbook, pp. 73–105. Springer, Boston (2011).  https://doi.org/10.1007/978-0-387-85820-3_3CrossRefGoogle Scholar
  8. 8.
    Meng, L., Huang, R., Gu, J.: A review of semantic similarity measures in wordnet. Int. J. Hybrid Inf. Technol. 6(1), 1–12 (2013)Google Scholar
  9. 9.
    Pirolli, P., Card, S.: Information foraging in information access environments. In: Proceedings of the SIGCHI Conference on Human factors in Computing Systems, pp. 51–58. ACM Press/Addison-Wesley Publishing Co. (1995)Google Scholar
  10. 10.
    Ranjan, A., Srinivasan, N.: Dissimilarity in creative categorization. J. Creat. Behav. 44(2), 71–83 (2010)CrossRefGoogle Scholar
  11. 11.
    Ritchie, G.: Current directions in computational humour. Artif. Intell. Rev. 16(2), 119–135 (2001)CrossRefGoogle Scholar
  12. 12.
    Russell, J.A.: Core affect and the psychological construction of emotion. Psychol. Rev. 110(1), 145 (2003)CrossRefGoogle Scholar
  13. 13.
    Schalekamp, F., Zuylen, A.v.: Rank aggregation: together we’re strong. In: 2009 Proceedings of the Eleventh Workshop on Algorithm Engineering and Experiments (ALENEX), pp. 38–51. SIAM (2009)CrossRefGoogle Scholar
  14. 14.
    Shetty, S.: Quantifying Comedy on Youtube: Why the Number of o’s in Your LOL Matter (2012)Google Scholar
  15. 15.
    Toms, E.G.: Serendipitous information retrieval. In: DELOS Workshop: Information Seeking, Searching and Querying in Digital Libraries. Zurich (2000)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceIIT KanpurKanpurIndia

Personalised recommendations